On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation

• URL: http://arxiv.org/abs/2505.22444v1
• Date: Wed, 28 May 2025 15:08:36 GMT
• Title: On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation
• Authors: Liyao Tang, Zhe Chen, Dacheng Tao,
• Abstract summary: We introduce a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers.<n>Our approach sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models.
• Score: 52.96632954620623
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The emergence of large-scale pre-trained point cloud models has significantly advanced 3D scene understanding, but adapting these models to specific downstream tasks typically demands full fine-tuning, incurring high computational and storage costs. Parameter-efficient fine-tuning (PEFT) techniques, successful in natural language processing and 2D vision tasks, would underperform when naively applied to 3D point cloud models due to significant geometric and spatial distribution shifts. Existing PEFT methods commonly treat points as orderless tokens, neglecting important local spatial structures and global geometric contexts in 3D modeling. To bridge this gap, we introduce the Geometric Encoding Mixer (GEM), a novel geometry-aware PEFT module specifically designed for 3D point cloud transformers. GEM explicitly integrates fine-grained local positional encodings with a lightweight latent attention mechanism to capture comprehensive global context, thereby effectively addressing the spatial and geometric distribution mismatch. Extensive experiments demonstrate that GEM achieves performance comparable to or sometimes even exceeding full fine-tuning, while only updating 1.6% of the model's parameters, fewer than other PEFT methods. With significantly reduced training time and memory requirements, our approach thus sets a new benchmark for efficient, scalable, and geometry-aware fine-tuning of large-scale 3D point cloud models. Code will be released.

Related papers

• TrackAny3D: Transferring Pretrained 3D Models for Category-unified 3D Point Cloud Tracking [25.788917457593673]
  TrackAny3D is the first framework to transfer large-scale pretrained 3D models for category-agnostic 3D SOT.<n>MoGE architecture adaptively activates specialized 3works based on distinct geometric characteristics.<n>Experiments show that TrackAny3D establishes new state-of-the-art performance on category-agnostic 3D SOT.
  arXiv  Detail & Related papers  (2025-07-26T10:41:55Z)
• UniPre3D: Unified Pre-training of 3D Point Cloud Models with Cross-Modal Gaussian Splatting [64.31900521467362]
  No existing pre-training method is equally effective for both object- and scene-level point clouds.<n>We introduce UniPre3D, the first unified pre-training method that can be seamlessly applied to point clouds of any scale and 3D models of any architecture.
  arXiv  Detail & Related papers  (2025-06-11T17:23:21Z)
• Graph and Skipped Transformer: Exploiting Spatial and Temporal Modeling Capacities for Efficient 3D Human Pose Estimation [36.93661496405653]
  We take a global approach to exploit Transformer-temporal information with a concise Graph and Skipped Transformer architecture. Specifically, in 3D pose stage, coarse-grained body parts are deployed to construct a fully data-driven adaptive model. Experiments are conducted on Human3.6M, MPI-INF-3DHP and Human-Eva benchmarks.
  arXiv  Detail & Related papers  (2024-07-03T10:42:09Z)
• GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation [65.33726478659304]
  We introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent sparsity of 3D structure and do not utilize explicit geometric relationships between 3D and 2D images. GeoLRM tackles these issues by incorporating a novel 3D-aware transformer structure that directly processes 3D points and uses deformable cross-attention mechanisms.
  arXiv  Detail & Related papers  (2024-06-21T17:49:31Z)
• Flatten Anything: Unsupervised Neural Surface Parameterization [76.4422287292541]
  We introduce the Flatten Anything Model (FAM), an unsupervised neural architecture to achieve global free-boundary surface parameterization. Compared with previous methods, our FAM directly operates on discrete surface points without utilizing connectivity information. Our FAM is fully-automated without the need for pre-cutting and can deal with highly-complex topologies.
  arXiv  Detail & Related papers  (2024-05-23T14:39:52Z)
• ParaPoint: Learning Global Free-Boundary Surface Parameterization of 3D Point Clouds [52.03819676074455]
  ParaPoint is an unsupervised neural learning pipeline for achieving global free-boundary surface parameterization. This work makes the first attempt to investigate neural point cloud parameterization that pursues both global mappings and free boundaries.
  arXiv  Detail & Related papers  (2024-03-15T14:35:05Z)
• Point-PEFT: Parameter-Efficient Fine-Tuning for 3D Pre-trained Models [46.42092771753465]
  We introduce Point-PEFT, a novel framework for adapting point cloud pre-trained models with minimal learnable parameters. Specifically, for a pre-trained 3D model, we freeze most of its parameters, and only tune the newly added PEFT modules on downstream tasks.
  arXiv  Detail & Related papers  (2023-10-04T16:49:36Z)
• StarNet: Style-Aware 3D Point Cloud Generation [82.30389817015877]
  StarNet is able to reconstruct and generate high-fidelity and even 3D point clouds using a mapping network. Our framework achieves comparable state-of-the-art performance on various metrics in the point cloud reconstruction and generation tasks.
  arXiv  Detail & Related papers  (2023-03-28T08:21:44Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.